8 citations · 8 across the 2 of their papers we have counts for
5 papers
Nonlocal optimization of binary neural networks
Amir Khoshaman, Giuseppe Castiglione, Christopher Srinivasa
We explore training Binary Neural Networks (BNNs) as a discrete variable inference problem over a factor graph. We study the behaviour of this conversion in an under-parameterized…
A Path Towards Quantum Advantage in Training Deep Generative Models with Quantum Annealers
Walter Vinci, Lorenzo Buffoni, Hossein Sadeghi +3
The development of quantum-classical hybrid (QCH) algorithms is critical to achieve state-of-the-art computational models. A QCH variational autoencoder (QVAE) was introduced in Re…
GumBolt: Extending Gumbel trick to Boltzmann priors
Amir H. Khoshaman, Mohammad H. Amin
Boltzmann machines (BMs) are appealing candidates for powerful priors in variational autoencoders (VAEs), as they are capable of capturing nontrivial and multi-modal distributions…
Quantum Variational Autoencoder
Amir Khoshaman, Walter Vinci, Brandon Denis +3
Variational autoencoders (VAEs) are powerful generative models with the salient ability to perform inference. Here, we introduce a quantum variational autoencoder (QVAE): a VAE who…
DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
Arash Vahdat, William G. Macready, Zhengbing Bian +2
Training of discrete latent variable models remains challenging because passing gradient information through discrete units is difficult. We propose a new class of smoothing transf…